iMessage (imsg)
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly reads and searches iMessage/SMS chats via Messages.app, which ingests untrusted, user-generated third-party message content that the agent would read and could let embedded instructions influence its actions.
Audit Metadata